Claude Opus 4.6 (Max) vs DeepSeek V4 Pro 0813 (Non-reasoning)

Claude Opus 4.6 (Max) vs DeepSeek V4 Pro 0813 (Non-reasoning). A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

AnthropicClaude Opus 4.6 (Max)Not ranked · benchmark data missing
Intelligence
31.90
Total cost
-
DeepSeekDeepSeek V4 Pro 0813 (Non-reasoning)Off the frontier
Intelligence
20.40
Total cost
$451
Verdict

Comparison incomplete

A reliable intelligence-versus-cost verdict requires both models' intelligence scores and benchmark-run costs. Missing data is not a performance verdict.

MetricClaude Opus 4.6 (Max)DeepSeek V4 Pro 0813 (Non-reasoning)Difference
Intelligence (higher is better)31.920.4−36.1% DeepSeek V4 Pro 0813 … is 36.1% less intelligent
Total AA cost (lower is better)Not reported$450.76— not comparable
End-to-end time (lower is better)36.25s6.55s−81.9% DeepSeek V4 Pro 0813 … is 81.9% faster
Price per 1M tokens (in / out)$5.00 / $25.0$1.32 / $3.96
Input modalitiesText, ImageText
Open this matchup in the interactive pickerClaude Opus 4.6 (Max): what beats itDeepSeek V4 Pro 0813 (Non-reasoning): what beats it
Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/claude-opus-4-6-adaptive/deepseek-v4-pro-non-reasoning · Markdown: /api/v1/compare/claude-opus-4-6-adaptive/deepseek-v4-pro-non-reasoning?format=md · llms.txt · agent skill